It’s fascinating to live through a the emergence of a new technology and to see people trying to make sense of it as they go.
I personally think that a lot of the words used around AI, harness, SKILLS, agents, RAG.. are make up words or close to it, words that do not have profound semantics, even though people are trying to, often after the fact, make sense of them.
It’s just popular words that are different enough that people like to use them to claim a new knowledge, or to market a product.
But we could use AI tooling instead of harness in the abstract, and it would be better to use more precise terms for more concrete use cases, agent loop, CLI, IDE..
It was a fun game at a time where papers were competing for attention, but now that it has become a proven technology, I hope we can find more precise and meaningful words.
The Agent/harness has no meaningful distinction. The backing model(s) can only read through a harness. Call it an agent, call it a tool, call it a library. They are all harnesses if they are backed by a model.
Broadly speaking,
- Copilot only reads AGENTS.md
- Codex reads AGENTS and CONTEXT
- Claude reads CLAUDE
This ai-literacy is noise, muddling the definitions and suggesting yet-another-md-file.
I think most people that use LLM coding tools enough independently derive most of the stuff in the article. For example my approach to garbage collection is to sample paths within the project and chunks of file content, then assemble context (similarity search results, git blame) for the agent to use to assess cruftiness and if found schedule cleanup.
What even is this "AI Literacy framework"? When I see such overengineering I look at what the author has done. In this case, I find the author runs a consultancy on engineering "Habitats for Humans and AI" (https://www.russmiles.com/), listing a bunch of books he did not write (the author names are conveniently cropped out). This doesn't even belong on LinkedIn.
I'm not the author -- but I am currently fortunate to be sitting in a workshop he is teaching on the topic and figured HN might like (especially since he gives a lot of his content out for free/OSS).
As someone who does loads of AI-driven dev and governance, I'm finding there are a lot of great nuggets here. Between him (chaos engineering) and Kent Beck (extreme programming) I'n a kid in the candy store and wanted to share.
Here’s the original article this one is based on: https://martinfowler.com/articles/harness-engineering.html
And here is the original author on a podcast talking about it: https://open.spotify.com/episode/4FxEdjXldNhoh67KYVmbDu
Here's a better summary: https://github.com/rush86999/atom/blob/main/docs/architectur...
I also have a self-evolving architecture on it, but you have to be careful, especially if you're using multiple models (still WIP).
That looks like a “Deep Research” report generated by an LLM, not a summary.
It’s fascinating to live through a the emergence of a new technology and to see people trying to make sense of it as they go.
I personally think that a lot of the words used around AI, harness, SKILLS, agents, RAG.. are make up words or close to it, words that do not have profound semantics, even though people are trying to, often after the fact, make sense of them.
It’s just popular words that are different enough that people like to use them to claim a new knowledge, or to market a product.
But we could use AI tooling instead of harness in the abstract, and it would be better to use more precise terms for more concrete use cases, agent loop, CLI, IDE..
It was a fun game at a time where papers were competing for attention, but now that it has become a proven technology, I hope we can find more precise and meaningful words.
Hear hear! We techies are bad at naming things. "NoSQL" is probably a top contender there.
This part seems relevant - they make explicit the difference between their HARNESS.md document and AGENTS.md. It's actually interesting: https://habitat-thinking.github.io/ai-literacy-superpowers/p...
The Agent/harness has no meaningful distinction. The backing model(s) can only read through a harness. Call it an agent, call it a tool, call it a library. They are all harnesses if they are backed by a model.
Broadly speaking,
- Copilot only reads AGENTS.md
- Codex reads AGENTS and CONTEXT
- Claude reads CLAUDE
This ai-literacy is noise, muddling the definitions and suggesting yet-another-md-file.
I put everything in CONTRIBUTING.md, and then put "See: CONTRIBUTING.md" in those vendor-specific files.
I'm an AI Agent Harness .md File consultant, you can ask me anything
it lists 'Garbage Collection' as one of the 3 components of a harness
I don't know any harness that solves 'Garbage Collection' in the way described here
(most harnesses accelerate context pollution and code base drift via instructions they embed into system prompts, tool descriptions and skills)
I think most people that use LLM coding tools enough independently derive most of the stuff in the article. For example my approach to garbage collection is to sample paths within the project and chunks of file content, then assemble context (similarity search results, git blame) for the agent to use to assess cruftiness and if found schedule cleanup.
Not saying this is AI-gen but it's very dense and doesn't read like something I could glean info from easily
I think this article posted to HN last week did a better job explaining things IMO https://earendil.com/posts/what-is-a-harness/
> Not saying this is AI-gen
The prose is definitely written by a Claude-like
It is pretty obvious that Claude wrote it. No human writes README that long, and it's one of the contributors: https://github.com/Habitat-Thinking/ai-literacy-superpowers
This looks good - is there a version of it for CODEX? If not i guess it could easily be transformed for it.
Looks like typical material coming out of consulting companies like ThoughtWorks, designed to obfuscate rather than educate.
I also stumbled upon this site, which on a first glance looks really thorough. Interested to hear if folks have comments on it though:
https://walkinglabs.github.io/learn-harness-engineering/en/
This is perfect, here's a tool for harness engineering to be more effective that I just released today https://github.com/issacnitin/RealDiff
What’s the best current practice if we want to enable agent code review and approval of GitHub PRs but only for specific users?
This is oddly reassuring
I like how agent review is a deprecation target. explicitly. Se then a harness matures by getting dumber and cheaper, not smarter.
Related currently:
The Harness is the Thing
https://news.ycombinator.com/item?id=49452346
What even is this "AI Literacy framework"? When I see such overengineering I look at what the author has done. In this case, I find the author runs a consultancy on engineering "Habitats for Humans and AI" (https://www.russmiles.com/), listing a bunch of books he did not write (the author names are conveniently cropped out). This doesn't even belong on LinkedIn.
I'm not the author -- but I am currently fortunate to be sitting in a workshop he is teaching on the topic and figured HN might like (especially since he gives a lot of his content out for free/OSS).
As someone who does loads of AI-driven dev and governance, I'm finding there are a lot of great nuggets here. Between him (chaos engineering) and Kent Beck (extreme programming) I'n a kid in the candy store and wanted to share.
"Explain the harness" is apparently the new "explain LLMs" genre of slop blogging, I now see articles to this effect on HN daily.